我正在嘗試將此tflearn DCNN示例(使用圖像預處理和augmemtation)轉換為keras:Tflearn示例:import tflearnfrom tflearn.data_utils import shuffle, to_categoricalfrom tflearn.layers.core import input_data, dropout, fully_connectedfrom tflearn.layers.conv import conv_2d, max_pool_2dfrom tflearn.layers.estimator import regressionfrom tflearn.data_preprocessing import ImagePreprocessingfrom tflearn.data_augmentation import ImageAugmentation# Data loading and preprocessingfrom tflearn.datasets import cifar10(X, Y), (X_test, Y_test) = cifar10.load_data()X, Y = shuffle(X, Y)Y = to_categorical(Y, 10)Y_test = to_categorical(Y_test, 10)# Real-time data preprocessingimg_prep = ImagePreprocessing()img_prep.add_featurewise_zero_center()img_prep.add_featurewise_stdnorm()# Real-time data augmentationimg_aug = ImageAugmentation()img_aug.add_random_flip_leftright()img_aug.add_random_rotation(max_angle=25.)# Convolutional network buildingnetwork = input_data(shape=[None, 32, 32, 3], data_preprocessing=img_prep, data_augmentation=img_aug)network = conv_2d(network, 32, 3, activation='relu')network = max_pool_2d(network, 2)network = conv_2d(network, 64, 3, activation='relu')network = conv_2d(network, 64, 3, activation='relu')network = max_pool_2d(network, 2)network = fully_connected(network, 512, activation='relu')network = dropout(network, 0.5)50個紀元后產生了以下結果:Training Step: 26050 | total loss: 0.35260 | time: 144.306s| Adam | epoch: 050 | loss: 0.35260 - acc: 0.8785 | val_loss: 0.64622 - val_acc: 0.8212 -- iter: 50000/50000然后,我嘗試使用相同的DCNN圖層,參數和圖像預處理/增強功能將其轉換為Keras這會產生差得多的驗證準確性結果:Epoch 50/50521/521 [==============================] - 84s 162ms/step - loss: 0.4723 - acc: 0.8340 - val_loss: 3.2970 - val_acc: 0.2729Test score: 3.2969648239135743Accuracy: 27.29%誰能幫我理解原因?我在Keras中是否誤用了/誤解了圖像預處理/增強功能?
1 回答

桃花長相依
TA貢獻1860條經驗 獲得超8個贊
在Keras模型中,您也忘記了標準化驗證數據。您可以通過使用訓練數據datagen.mean并對其進行datagen.std計算來做到這一點:
# normalize test data; add a small constant to avoid division by zero,
# you can alternatively use `keras.backend.epsilon()`
X_test = (X_test - datagen.mean) / (datagen.std + 1e-8)
或者您可以使用該datagen.standardize()方法對測試數據進行規范化:
X_test = datagen.standardize(X_test)
有關更多信息,請參見SO上的這個問題:預測期間,數據標準化如何在keras中起作用?
別忘了您應該通過對訓練數據計算出的統計數據對測試數據進行歸一化。永遠不要通過自己的統計數據對測試數據進行歸一化。
警告:似乎也standardize 改變了它的參數...是的,您可以在源代碼中確認這一點。
添加回答
舉報
0/150
提交
取消